Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Impertio-Studio/n8n-Claude-Skill-Package --skill n8n-core-architecturegit clone --depth 1 https://github.com/Impertio-Studio/n8n-Claude-Skill-PackageWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/impertio-studio/n8n-claude-skill-package/n8n-core-architecture)<a href="https://agentmods.dev/skills/impertio-studio/n8n-claude-skill-package/n8n-core-architecture"><img src="https://agentmods.dev/badge/skills/impertio-studio/n8n-claude-skill-package/n8n-core-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/impertio-studio/n8n-claude-skill-package/n8n-core-architecture"><img src="https://agentmods.dev/badge/skills/impertio-studio/n8n-claude-skill-package/n8n-core-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00123 | $0.02937 |
| Opus 5 | $0.00062 | $0.01469 |
| Sonnet 5 | $0.00025 | $0.00587 |
| Haiku 4.5 | $0.00012 | $0.00294 |
Grade A, and why
n8n-core-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n8n-core-architecture
Quick Reference
Architecture Layers (n8n v1.x)
| Layer | Technology | Role |
|---|---|---|
| Execution Engine | Node.js + TypeScript | Processes workflows as item sequences through nodes |
| Item Pipeline | INodeExecutionData | Carries JSON data, binary files, paired items, and errors |
| Node System | INodeType interface | Defines trigger, regular, webhook, polling, and declarative nodes |
| Expression Engine | Data Proxy | Provides $json, $input, $binary, $execution, $workflow, $node |
| Process Model | Main / Worker / Queue | Scales from single-process to distributed queue mode |
| Workflow Settings | IWorkflowSettings | Controls timezone, error handling, execution timeout, execution order |
Execution Modes (WorkflowExecuteMode)
| Mode | Trigger |
|---|---|
manual |
User clicks "Execute Workflow" in editor |
webhook |
HTTP webhook received |
trigger |
Trigger node activated (schedule, poll) |
retry |
Retrying a failed execution |
cli |
Command-line execution |
error |
Error workflow triggered |
integrated |
Sub-workflow called from another workflow |
internal |
Internal system execution |
evaluation |
Evaluation/test execution |
chat |
Chat-based trigger |
Node Types
| Type | Method | Inputs | Group |
|---|---|---|---|
| Regular | execute() |
Has inputs | ['transform'], ['input'], ['output'] |
| Event Trigger | trigger() |
No inputs | ['trigger'] |
| Webhook Trigger | webhook() |
No inputs | ['trigger'] |
| Polling Trigger | poll() |
No inputs | ['trigger'] (with polling: true) |
| Declarative | None (routing config) | Has inputs | Any |
Critical Warnings
NEVER return a flat INodeExecutionData[] from execute() -- ALWAYS wrap in an outer array: return [returnData]. The outer array represents output indices (for multi-output nodes like IF/Switch).
NEVER mutate input items directly -- ALWAYS create new item objects. Mutating input items causes data corruption in downstream nodes that share the same reference.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 318 lines · 123 tokens per session scan A 9515a70e3734
n8n-core-architecture is a skill published in the GitHub repository Impertio-Studio/n8n-Claude-Skill-Package (3 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 2,937 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-code-tool
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
cognito
AWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.